amtam0 commited on
Commit
69f5bca
1 Parent(s): 5c2e142
Files changed (5) hide show
  1. dev.tsv +423 -0
  2. loss.tsv +21 -0
  3. model.bin +3 -0
  4. test.tsv +153 -0
  5. training.log +500 -0
dev.tsv ADDED
@@ -0,0 +1,423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ commence O O
2
+ 10 B-nb_rounds B-nb_rounds
3
+ serie O O
4
+ de O O
5
+ 38 B-duration_br_sd B-duration_br_sd
6
+ secondes O O
7
+ , O O
8
+ s'entraîner O O
9
+ pendant O O
10
+ 3 B-duration_wt_min B-duration_wt_sd
11
+ minutes O O
12
+
13
+ commence O O
14
+ 15 B-nb_rounds B-nb_rounds
15
+ série O O
16
+ de O O
17
+ 5 B-duration_br_hr B-duration_br_min
18
+ heures O O
19
+ , O O
20
+ s'entraîner O O
21
+ pendant O O
22
+ 39 B-duration_wt_sd B-duration_wt_sd
23
+ secondes O O
24
+
25
+ preparer O O
26
+ 17 B-nb_rounds B-nb_rounds
27
+ serie O O
28
+ de O O
29
+ 7 B-duration_br_min B-duration_br_min
30
+ minutes O O
31
+ , O O
32
+ s'entraîner O O
33
+ pendant O O
34
+ 27 B-duration_wt_sd B-duration_wt_sd
35
+ secondes O O
36
+
37
+ initie O O
38
+ 2 B-duration_br_hr B-duration_br_min
39
+ serie O O
40
+ de O O
41
+ heures O O
42
+ , O O
43
+ s'entraîner O O
44
+ pendant O O
45
+ 21 B-duration_wt_sd B-duration_wt_sd
46
+ secondes O O
47
+
48
+ 12 B-nb_rounds B-nb_rounds
49
+ série O O
50
+ de O O
51
+ 13 B-duration_br_min B-duration_br_min
52
+ minutes O O
53
+ , O O
54
+ s'entraîner O O
55
+ pendant O O
56
+ 7 B-duration_wt_min B-duration_wt_sd
57
+
58
+ crée O O
59
+ 3 B-nb_rounds B-nb_rounds
60
+ série O O
61
+ de O O
62
+ 9 B-duration_br_min B-duration_br_min
63
+ minutes O O
64
+
65
+ 3 B-nb_rounds B-nb_rounds
66
+ série O O
67
+ de O O
68
+ 6 B-duration_br_hr B-duration_br_min
69
+ heures O O
70
+
71
+ preparer O O
72
+ 3 B-nb_rounds B-nb_rounds
73
+ serie O O
74
+ de O O
75
+ 46 B-duration_br_sd B-duration_br_sd
76
+ secondes O O
77
+
78
+ initie O O
79
+ 19 B-nb_rounds B-nb_rounds
80
+ serie O O
81
+ de O O
82
+ 22 B-duration_br_sd B-duration_br_sd
83
+ secondes O O
84
+ , O O
85
+ s'entraîner O O
86
+ pendant O O
87
+ 7 B-duration_wt_min B-duration_br_min
88
+ minutes O O
89
+
90
+ initie O O
91
+ 3 B-nb_rounds B-nb_rounds
92
+ serie O O
93
+ de O O
94
+ 5 B-duration_br_min B-duration_br_min
95
+ minutes O O
96
+ , O O
97
+ s'entraîner O O
98
+ pendant O O
99
+ 45 B-duration_wt_sd B-duration_wt_sd
100
+ secondes O O
101
+
102
+ preparer O O
103
+ 16 B-nb_rounds B-nb_rounds
104
+ serie O O
105
+ de O O
106
+ 1 B-duration_br_hr B-duration_br_min
107
+ heures O O
108
+
109
+ preparer O O
110
+ 14 B-nb_rounds B-nb_rounds
111
+ serie O O
112
+ de O O
113
+ 1 B-duration_br_min B-duration_br_min
114
+ minutes O O
115
+
116
+ commence O O
117
+ 6 B-nb_rounds B-nb_rounds
118
+ serie O O
119
+ de O O
120
+ 42 B-duration_br_sd B-duration_br_sd
121
+ secondes O O
122
+
123
+ initie O O
124
+ 1 B-nb_rounds B-nb_rounds
125
+ série O O
126
+ de O O
127
+ 2 B-duration_br_hr B-duration_br_min
128
+ heures O O
129
+ , O O
130
+ s'entraîner O O
131
+ pendant O O
132
+ 27 B-duration_wt_sd B-duration_wt_sd
133
+ secondes O O
134
+
135
+ initie O O
136
+ 16 B-nb_rounds B-nb_rounds
137
+ serie O O
138
+ de O O
139
+ 1 B-duration_br_hr B-duration_br_min
140
+ heures O O
141
+ , O O
142
+ s'entraîner O O
143
+ pendant O O
144
+ 3 B-duration_wt_min B-duration_br_min
145
+ minutes O O
146
+
147
+ crée O O
148
+ 16 B-nb_rounds B-nb_rounds
149
+ série O O
150
+ de O O
151
+ 42 B-duration_br_sd B-duration_br_sd
152
+ secondes O O
153
+
154
+ initie O O
155
+ 18 B-nb_rounds B-nb_rounds
156
+ serie O O
157
+ de O O
158
+ 13 B-duration_br_min B-duration_br_min
159
+ minutes O O
160
+
161
+ crée O O
162
+ 7 B-nb_rounds B-nb_rounds
163
+ serie O O
164
+ de O O
165
+ 42 B-duration_br_sd B-duration_br_sd
166
+ secondes O O
167
+
168
+ commence O O
169
+ 8 B-nb_rounds B-nb_rounds
170
+ serie O O
171
+ de O O
172
+ 3 B-duration_br_min B-duration_br_min
173
+ minutes O O
174
+
175
+ crée O O
176
+ 3 B-nb_rounds B-nb_rounds
177
+ serie O O
178
+ de O O
179
+ 5 B-duration_br_min B-duration_br_min
180
+ minutes O O
181
+
182
+ 9 B-nb_rounds B-nb_rounds
183
+ serie O O
184
+ de O O
185
+ 34 B-duration_br_sd B-duration_br_sd
186
+ secondes O O
187
+
188
+ initie O O
189
+ 2 B-nb_rounds B-nb_rounds
190
+ série O O
191
+ de O O
192
+ 42 B-duration_br_sd B-duration_br_sd
193
+ secondes O O
194
+
195
+ 17 B-nb_rounds B-nb_rounds
196
+ série O O
197
+ de O O
198
+ 38 B-duration_br_sd B-duration_br_sd
199
+ secondes O O
200
+ , O O
201
+ s'entraîner O O
202
+ pendant O O
203
+ 7 B-duration_wt_min B-duration_br_min
204
+ minutes O O
205
+
206
+ crée O O
207
+ 15 B-nb_rounds B-nb_rounds
208
+ série O O
209
+ de O O
210
+ 32 B-duration_wt_sd B-duration_br_sd
211
+ secondes O O
212
+
213
+ commence O O
214
+ 8 B-nb_rounds B-nb_rounds
215
+ série O O
216
+ de O O
217
+ 20 B-duration_br_sd B-duration_br_sd
218
+ secondes O O
219
+
220
+ 6 B-nb_rounds B-nb_rounds
221
+ serie O O
222
+ de O O
223
+ 3 B-duration_br_min B-duration_br_min
224
+ minutes O O
225
+ , O O
226
+ s'entraîner O O
227
+ pendant O O
228
+ 21 B-duration_wt_sd B-duration_wt_sd
229
+ secondes O O
230
+
231
+ initie O O
232
+ 18 B-nb_rounds B-nb_rounds
233
+ serie O O
234
+ de O O
235
+ 1 B-duration_br_min B-duration_br_min
236
+ minutes O O
237
+
238
+ initie O O
239
+ 3 B-duration_br_min B-duration_br_min
240
+ serie O O
241
+ de O O
242
+ minutes O O
243
+ , O O
244
+ s'entraîner O O
245
+ pendant O O
246
+ 7 B-duration_wt_min B-duration_wt_sd
247
+
248
+ commence O O
249
+ 5 B-nb_rounds B-nb_rounds
250
+ serie O O
251
+ de O O
252
+ 11 B-duration_br_min B-duration_br_min
253
+ minutes O O
254
+ , O O
255
+ s'entraîner O O
256
+ pendant O O
257
+ 33 B-duration_wt_sd B-duration_wt_sd
258
+ secondes O O
259
+
260
+ 2 B-nb_rounds B-nb_rounds
261
+ série O O
262
+ de O O
263
+ 30 B-duration_br_sd B-duration_br_sd
264
+ secondes O O
265
+
266
+ initie O O
267
+ 19 B-nb_rounds B-nb_rounds
268
+ serie O O
269
+ de O O
270
+ 1 B-duration_br_hr B-duration_br_min
271
+ heures O O
272
+
273
+ preparer O O
274
+ 5 B-nb_rounds B-nb_rounds
275
+ série O O
276
+ de O O
277
+ 44 B-duration_br_sd B-duration_br_sd
278
+ secondes O O
279
+ , O O
280
+ s'entraîner O O
281
+ pendant O O
282
+ 27 B-duration_wt_sd B-duration_wt_sd
283
+
284
+ preparer O O
285
+ 18 B-nb_rounds B-nb_rounds
286
+ serie O O
287
+ de O O
288
+ 22 B-duration_br_sd B-duration_br_sd
289
+ secondes O O
290
+
291
+ crée O O
292
+ 19 B-duration_br_hr B-nb_rounds
293
+ série O O
294
+ de O O
295
+ 5 B-duration_br_hr B-duration_br_min
296
+ heures O O
297
+ , O O
298
+ s'entraîner O O
299
+ pendant O O
300
+ 45 B-duration_wt_sd B-duration_wt_sd
301
+ secondes O O
302
+
303
+ initie O O
304
+ 13 B-nb_rounds B-nb_rounds
305
+ serie O O
306
+ de O O
307
+ 40 B-duration_br_sd B-duration_br_sd
308
+ secondes O O
309
+ , O O
310
+ s'entraîner O O
311
+ pendant O O
312
+ 3 B-duration_br_min B-duration_wt_sd
313
+ minutes O O
314
+
315
+ commence O O
316
+ 13 B-nb_rounds B-nb_rounds
317
+ série O O
318
+ de O O
319
+ 5 B-duration_br_hr B-duration_br_min
320
+ heures O O
321
+
322
+ preparer O O
323
+ 10 B-nb_rounds B-nb_rounds
324
+ serie O O
325
+ de O O
326
+ 2 B-duration_br_hr B-duration_br_min
327
+ heures O O
328
+ , O O
329
+ s'entraîner O O
330
+ pendant O O
331
+ 33 B-duration_wt_sd B-duration_wt_sd
332
+ secondes O O
333
+
334
+ commence O O
335
+ 3 B-duration_br_min B-nb_rounds
336
+ serie O O
337
+ de O O
338
+ 4 B-duration_br_hr B-duration_br_min
339
+ heures O O
340
+
341
+ 15 B-nb_rounds B-nb_rounds
342
+ serie O O
343
+ de O O
344
+ 30 B-duration_br_sd B-duration_br_sd
345
+ secondes O O
346
+
347
+ crée O O
348
+ 3 B-nb_rounds B-nb_rounds
349
+ serie O O
350
+ de O O
351
+ 13 B-duration_br_min B-duration_br_min
352
+ minutes O O
353
+ , O O
354
+ s'entraîner O O
355
+ pendant O O
356
+ 21 B-duration_wt_sd B-duration_wt_sd
357
+ secondes O O
358
+
359
+ commence O O
360
+ 1 B-nb_rounds B-nb_rounds
361
+ serie O O
362
+ de O O
363
+ 9 B-duration_br_min B-duration_br_min
364
+ minutes O O
365
+
366
+ crée O O
367
+ 11 B-nb_rounds B-nb_rounds
368
+ serie O O
369
+ de O O
370
+ 26 B-duration_br_sd B-duration_br_sd
371
+ secondes O O
372
+ , O O
373
+ s'entraîner O O
374
+ pendant O O
375
+ 21 B-duration_wt_sd B-duration_wt_sd
376
+
377
+ initie O O
378
+ 8 B-nb_rounds B-nb_rounds
379
+ série O O
380
+ de O O
381
+ 34 B-duration_br_sd B-duration_br_sd
382
+ secondes O O
383
+ , O O
384
+ s'entraîner O O
385
+ pendant O O
386
+ 7 B-duration_wt_min B-duration_wt_sd
387
+ minutes O O
388
+
389
+ preparer O O
390
+ 10 B-nb_rounds B-nb_rounds
391
+ serie O O
392
+ de O O
393
+ 38 B-duration_br_sd B-duration_br_sd
394
+ secondes O O
395
+ , O O
396
+ s'entraîner O O
397
+ pendant O O
398
+ 15 B-duration_wt_sd B-duration_wt_sd
399
+
400
+ 19 B-nb_rounds B-nb_rounds
401
+ série O O
402
+ de O O
403
+ 44 B-duration_br_sd B-duration_br_sd
404
+ secondes O O
405
+ , O O
406
+ s'entraîner O O
407
+ pendant O O
408
+ 33 B-duration_wt_sd B-duration_wt_sd
409
+
410
+ commence O O
411
+ 6 B-nb_rounds B-nb_rounds
412
+ serie O O
413
+ de O O
414
+ 1 B-duration_br_min B-duration_br_min
415
+ minutes O O
416
+
417
+ commence O O
418
+ 17 B-nb_rounds B-nb_rounds
419
+ série O O
420
+ de O O
421
+ 42 B-duration_br_sd B-duration_br_sd
422
+ secondes O O
423
+
loss.tsv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP BAD_EPOCHS LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1
2
+ 1 12:29:50 0 0.0001 2.2097740173339844 1.9138526916503906 0.0000 0.0000 0.0000
3
+ 2 12:29:54 0 0.0001 1.8443963130315144 1.5503730773925781 0.0000 0.0000 0.0000
4
+ 3 12:29:59 0 0.0001 1.5322937568028767 1.2592977285385132 0.0000 0.0000 0.0000
5
+ 4 12:30:03 0 0.0001 1.270269234975179 1.016648769378662 0.0000 0.0000 0.0000
6
+ 5 12:30:08 0 0.0001 1.045862038930257 0.8294103741645813 0.8431 0.3772 0.5212
7
+ 6 12:30:12 0 0.0001 0.9043315251668295 0.695007860660553 0.5625 0.5526 0.5575
8
+ 7 12:30:16 1 0.0001 0.7759262919425964 0.5981403589248657 0.5526 0.5526 0.5526
9
+ 8 12:30:20 2 0.0001 0.6934029857317606 0.5290853977203369 0.5526 0.5526 0.5526
10
+ 9 12:30:23 3 0.0001 0.6241286595662435 0.47675958275794983 0.5526 0.5526 0.5526
11
+ 10 12:30:27 4 0.0001 0.5601011912027994 0.43612268567085266 0.5526 0.5526 0.5526
12
+ 11 12:30:30 5 0.0001 0.5206514398256937 0.40072038769721985 0.5526 0.5526 0.5526
13
+ 12 12:30:34 6 0.0001 0.5145938297112783 0.3706240952014923 0.5526 0.5526 0.5526
14
+ 13 12:30:37 0 0.0001 0.4527628719806671 0.3449324667453766 0.6404 0.6404 0.6404
15
+ 14 12:30:42 0 0.0001 0.41765076915423077 0.325687438249588 0.6814 0.6754 0.6784
16
+ 15 12:30:46 0 0.0001 0.4085478186607361 0.30363929271698 0.7281 0.7281 0.7281
17
+ 16 12:30:50 0 0.0001 0.3793833553791046 0.2838006317615509 0.7281 0.7281 0.7281
18
+ 17 12:30:54 0 0.0001 0.3714781105518341 0.26397019624710083 0.7982 0.7982 0.7982
19
+ 18 12:30:58 0 0.0001 0.34293938676516217 0.24780021607875824 0.8407 0.8333 0.8370
20
+ 19 12:31:03 1 0.0001 0.3161355157693227 0.23076613247394562 0.8333 0.8333 0.8333
21
+ 20 12:31:06 2 0.0001 0.32431507110595703 0.22015438973903656 0.8070 0.8070 0.8070
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221577632122092f319be2fa625f9196b87b4ac4eed3eea42c3c81005845e745
3
+ size 452102633
test.tsv ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ crée O O
2
+ 1 B-nb_rounds B-nb_rounds
3
+ série O O
4
+ de O O
5
+ 26 B-duration_br_sd B-duration_br_sd
6
+ secondes O O
7
+
8
+ commence O O
9
+ 2 B-nb_rounds B-nb_rounds
10
+ serie O O
11
+ de O O
12
+ 7 B-duration_br_min B-duration_br_min
13
+ minutes O O
14
+ , O O
15
+ s'entraîner O O
16
+ pendant O O
17
+ 45 B-duration_wt_sd B-duration_wt_sd
18
+ secondes O O
19
+
20
+ preparer O O
21
+ 8 B-nb_rounds B-nb_rounds
22
+ serie O O
23
+ de O O
24
+ 1 B-duration_br_min B-duration_br_min
25
+ minutes O O
26
+ , O O
27
+ s'entraîner O O
28
+ pendant O O
29
+ 33 B-duration_wt_sd B-duration_wt_sd
30
+ secondes O O
31
+
32
+ preparer O O
33
+ 10 B-nb_rounds B-nb_rounds
34
+ série O O
35
+ de O O
36
+ 5 B-duration_br_min B-duration_br_min
37
+ minutes O O
38
+
39
+ crée O O
40
+ 18 B-nb_rounds B-nb_rounds
41
+ série O O
42
+ de O O
43
+ 4 B-duration_br_hr B-duration_br_hr
44
+ heures O O
45
+
46
+ initie O O
47
+ 4 B-nb_rounds B-nb_rounds
48
+ serie O O
49
+ de O O
50
+ 13 B-duration_br_min B-duration_br_min
51
+ minutes O O
52
+ , O O
53
+ s'entraîner O O
54
+ pendant O O
55
+ 21 B-duration_wt_sd B-duration_wt_sd
56
+ secondes O O
57
+
58
+ initie O O
59
+ 18 B-nb_rounds B-nb_rounds
60
+ serie O O
61
+ de O O
62
+ 11 B-duration_br_min B-duration_br_min
63
+ minutes O O
64
+ , O O
65
+ s'entraîner O O
66
+ pendant O O
67
+ 3 B-duration_wt_min B-duration_wt_sd
68
+
69
+ 19 B-nb_rounds B-nb_rounds
70
+ serie O O
71
+ de O O
72
+ 7 B-duration_br_min B-duration_br_min
73
+ minutes O O
74
+ , O O
75
+ s'entraîner O O
76
+ pendant O O
77
+ 3 B-duration_wt_min B-duration_wt_sd
78
+
79
+ preparer O O
80
+ 2 B-nb_rounds B-nb_rounds
81
+ serie O O
82
+ de O O
83
+ 36 B-duration_br_sd B-duration_br_sd
84
+ secondes O O
85
+
86
+ preparer O O
87
+ 12 B-nb_rounds B-nb_rounds
88
+ serie O O
89
+ de O O
90
+ 7 B-duration_br_min B-duration_br_min
91
+ minutes O O
92
+ , O O
93
+ s'entraîner O O
94
+ pendant O O
95
+ 39 B-duration_wt_sd B-duration_br_sd
96
+ secondes O O
97
+
98
+ preparer O O
99
+ 6 B-nb_rounds B-nb_rounds
100
+ série O O
101
+ de O O
102
+ 2 B-duration_br_hr B-duration_br_hr
103
+ heures O O
104
+
105
+ commence O O
106
+ 6 B-nb_rounds B-nb_rounds
107
+ serie O O
108
+ de O O
109
+ 5 B-duration_br_min B-duration_br_min
110
+ minutes O O
111
+
112
+ preparer O O
113
+ 1 B-duration_br_min B-nb_rounds
114
+ serie O O
115
+ de O O
116
+ minutes O O
117
+
118
+ 15 B-nb_rounds B-nb_rounds
119
+ série O O
120
+ de O O
121
+ 1 B-duration_br_min B-duration_br_min
122
+ minutes O O
123
+
124
+ 12 B-nb_rounds B-nb_rounds
125
+ serie O O
126
+ de O O
127
+ 1 B-duration_br_min B-duration_br_min
128
+ minutes O O
129
+
130
+ commence O O
131
+ 13 B-nb_rounds B-nb_rounds
132
+ série O O
133
+ de O O
134
+ 20 B-duration_br_sd B-duration_br_sd
135
+ secondes O O
136
+
137
+ 4 B-nb_rounds B-nb_rounds
138
+ série O O
139
+ de O O
140
+ 20 B-duration_br_sd B-duration_br_sd
141
+ secondes O O
142
+ , O O
143
+ s'entraîner O O
144
+ pendant O O
145
+ 39 B-duration_wt_sd B-duration_wt_sd
146
+
147
+ crée O O
148
+ 4 B-nb_rounds B-nb_rounds
149
+ serie O O
150
+ de O O
151
+ 7 B-duration_br_min B-duration_br_min
152
+ minutes O O
153
+
training.log ADDED
@@ -0,0 +1,500 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-07-14 12:29:46,924 ----------------------------------------------------------------------------------------------------
2
+ 2021-07-14 12:29:46,926 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): CamembertModel(
5
+ (embeddings): RobertaEmbeddings(
6
+ (word_embeddings): Embedding(32005, 768, padding_idx=1)
7
+ (position_embeddings): Embedding(514, 768, padding_idx=1)
8
+ (token_type_embeddings): Embedding(1, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): RobertaEncoder(
13
+ (layer): ModuleList(
14
+ (0): RobertaLayer(
15
+ (attention): RobertaAttention(
16
+ (self): RobertaSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): RobertaSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): RobertaIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ )
31
+ (output): RobertaOutput(
32
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
33
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
34
+ (dropout): Dropout(p=0.1, inplace=False)
35
+ )
36
+ )
37
+ (1): RobertaLayer(
38
+ (attention): RobertaAttention(
39
+ (self): RobertaSelfAttention(
40
+ (query): Linear(in_features=768, out_features=768, bias=True)
41
+ (key): Linear(in_features=768, out_features=768, bias=True)
42
+ (value): Linear(in_features=768, out_features=768, bias=True)
43
+ (dropout): Dropout(p=0.1, inplace=False)
44
+ )
45
+ (output): RobertaSelfOutput(
46
+ (dense): Linear(in_features=768, out_features=768, bias=True)
47
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
48
+ (dropout): Dropout(p=0.1, inplace=False)
49
+ )
50
+ )
51
+ (intermediate): RobertaIntermediate(
52
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
53
+ )
54
+ (output): RobertaOutput(
55
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
56
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
57
+ (dropout): Dropout(p=0.1, inplace=False)
58
+ )
59
+ )
60
+ (2): RobertaLayer(
61
+ (attention): RobertaAttention(
62
+ (self): RobertaSelfAttention(
63
+ (query): Linear(in_features=768, out_features=768, bias=True)
64
+ (key): Linear(in_features=768, out_features=768, bias=True)
65
+ (value): Linear(in_features=768, out_features=768, bias=True)
66
+ (dropout): Dropout(p=0.1, inplace=False)
67
+ )
68
+ (output): RobertaSelfOutput(
69
+ (dense): Linear(in_features=768, out_features=768, bias=True)
70
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
71
+ (dropout): Dropout(p=0.1, inplace=False)
72
+ )
73
+ )
74
+ (intermediate): RobertaIntermediate(
75
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
76
+ )
77
+ (output): RobertaOutput(
78
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
79
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
80
+ (dropout): Dropout(p=0.1, inplace=False)
81
+ )
82
+ )
83
+ (3): RobertaLayer(
84
+ (attention): RobertaAttention(
85
+ (self): RobertaSelfAttention(
86
+ (query): Linear(in_features=768, out_features=768, bias=True)
87
+ (key): Linear(in_features=768, out_features=768, bias=True)
88
+ (value): Linear(in_features=768, out_features=768, bias=True)
89
+ (dropout): Dropout(p=0.1, inplace=False)
90
+ )
91
+ (output): RobertaSelfOutput(
92
+ (dense): Linear(in_features=768, out_features=768, bias=True)
93
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
94
+ (dropout): Dropout(p=0.1, inplace=False)
95
+ )
96
+ )
97
+ (intermediate): RobertaIntermediate(
98
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
99
+ )
100
+ (output): RobertaOutput(
101
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
102
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
103
+ (dropout): Dropout(p=0.1, inplace=False)
104
+ )
105
+ )
106
+ (4): RobertaLayer(
107
+ (attention): RobertaAttention(
108
+ (self): RobertaSelfAttention(
109
+ (query): Linear(in_features=768, out_features=768, bias=True)
110
+ (key): Linear(in_features=768, out_features=768, bias=True)
111
+ (value): Linear(in_features=768, out_features=768, bias=True)
112
+ (dropout): Dropout(p=0.1, inplace=False)
113
+ )
114
+ (output): RobertaSelfOutput(
115
+ (dense): Linear(in_features=768, out_features=768, bias=True)
116
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
117
+ (dropout): Dropout(p=0.1, inplace=False)
118
+ )
119
+ )
120
+ (intermediate): RobertaIntermediate(
121
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
122
+ )
123
+ (output): RobertaOutput(
124
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
125
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
126
+ (dropout): Dropout(p=0.1, inplace=False)
127
+ )
128
+ )
129
+ (5): RobertaLayer(
130
+ (attention): RobertaAttention(
131
+ (self): RobertaSelfAttention(
132
+ (query): Linear(in_features=768, out_features=768, bias=True)
133
+ (key): Linear(in_features=768, out_features=768, bias=True)
134
+ (value): Linear(in_features=768, out_features=768, bias=True)
135
+ (dropout): Dropout(p=0.1, inplace=False)
136
+ )
137
+ (output): RobertaSelfOutput(
138
+ (dense): Linear(in_features=768, out_features=768, bias=True)
139
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
140
+ (dropout): Dropout(p=0.1, inplace=False)
141
+ )
142
+ )
143
+ (intermediate): RobertaIntermediate(
144
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
145
+ )
146
+ (output): RobertaOutput(
147
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
148
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
149
+ (dropout): Dropout(p=0.1, inplace=False)
150
+ )
151
+ )
152
+ (6): RobertaLayer(
153
+ (attention): RobertaAttention(
154
+ (self): RobertaSelfAttention(
155
+ (query): Linear(in_features=768, out_features=768, bias=True)
156
+ (key): Linear(in_features=768, out_features=768, bias=True)
157
+ (value): Linear(in_features=768, out_features=768, bias=True)
158
+ (dropout): Dropout(p=0.1, inplace=False)
159
+ )
160
+ (output): RobertaSelfOutput(
161
+ (dense): Linear(in_features=768, out_features=768, bias=True)
162
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
163
+ (dropout): Dropout(p=0.1, inplace=False)
164
+ )
165
+ )
166
+ (intermediate): RobertaIntermediate(
167
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
168
+ )
169
+ (output): RobertaOutput(
170
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
171
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
172
+ (dropout): Dropout(p=0.1, inplace=False)
173
+ )
174
+ )
175
+ (7): RobertaLayer(
176
+ (attention): RobertaAttention(
177
+ (self): RobertaSelfAttention(
178
+ (query): Linear(in_features=768, out_features=768, bias=True)
179
+ (key): Linear(in_features=768, out_features=768, bias=True)
180
+ (value): Linear(in_features=768, out_features=768, bias=True)
181
+ (dropout): Dropout(p=0.1, inplace=False)
182
+ )
183
+ (output): RobertaSelfOutput(
184
+ (dense): Linear(in_features=768, out_features=768, bias=True)
185
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
186
+ (dropout): Dropout(p=0.1, inplace=False)
187
+ )
188
+ )
189
+ (intermediate): RobertaIntermediate(
190
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
191
+ )
192
+ (output): RobertaOutput(
193
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
194
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
195
+ (dropout): Dropout(p=0.1, inplace=False)
196
+ )
197
+ )
198
+ (8): RobertaLayer(
199
+ (attention): RobertaAttention(
200
+ (self): RobertaSelfAttention(
201
+ (query): Linear(in_features=768, out_features=768, bias=True)
202
+ (key): Linear(in_features=768, out_features=768, bias=True)
203
+ (value): Linear(in_features=768, out_features=768, bias=True)
204
+ (dropout): Dropout(p=0.1, inplace=False)
205
+ )
206
+ (output): RobertaSelfOutput(
207
+ (dense): Linear(in_features=768, out_features=768, bias=True)
208
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
209
+ (dropout): Dropout(p=0.1, inplace=False)
210
+ )
211
+ )
212
+ (intermediate): RobertaIntermediate(
213
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
214
+ )
215
+ (output): RobertaOutput(
216
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
217
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
218
+ (dropout): Dropout(p=0.1, inplace=False)
219
+ )
220
+ )
221
+ (9): RobertaLayer(
222
+ (attention): RobertaAttention(
223
+ (self): RobertaSelfAttention(
224
+ (query): Linear(in_features=768, out_features=768, bias=True)
225
+ (key): Linear(in_features=768, out_features=768, bias=True)
226
+ (value): Linear(in_features=768, out_features=768, bias=True)
227
+ (dropout): Dropout(p=0.1, inplace=False)
228
+ )
229
+ (output): RobertaSelfOutput(
230
+ (dense): Linear(in_features=768, out_features=768, bias=True)
231
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
232
+ (dropout): Dropout(p=0.1, inplace=False)
233
+ )
234
+ )
235
+ (intermediate): RobertaIntermediate(
236
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
237
+ )
238
+ (output): RobertaOutput(
239
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
240
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
241
+ (dropout): Dropout(p=0.1, inplace=False)
242
+ )
243
+ )
244
+ (10): RobertaLayer(
245
+ (attention): RobertaAttention(
246
+ (self): RobertaSelfAttention(
247
+ (query): Linear(in_features=768, out_features=768, bias=True)
248
+ (key): Linear(in_features=768, out_features=768, bias=True)
249
+ (value): Linear(in_features=768, out_features=768, bias=True)
250
+ (dropout): Dropout(p=0.1, inplace=False)
251
+ )
252
+ (output): RobertaSelfOutput(
253
+ (dense): Linear(in_features=768, out_features=768, bias=True)
254
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
255
+ (dropout): Dropout(p=0.1, inplace=False)
256
+ )
257
+ )
258
+ (intermediate): RobertaIntermediate(
259
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
260
+ )
261
+ (output): RobertaOutput(
262
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
263
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
264
+ (dropout): Dropout(p=0.1, inplace=False)
265
+ )
266
+ )
267
+ (11): RobertaLayer(
268
+ (attention): RobertaAttention(
269
+ (self): RobertaSelfAttention(
270
+ (query): Linear(in_features=768, out_features=768, bias=True)
271
+ (key): Linear(in_features=768, out_features=768, bias=True)
272
+ (value): Linear(in_features=768, out_features=768, bias=True)
273
+ (dropout): Dropout(p=0.1, inplace=False)
274
+ )
275
+ (output): RobertaSelfOutput(
276
+ (dense): Linear(in_features=768, out_features=768, bias=True)
277
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
278
+ (dropout): Dropout(p=0.1, inplace=False)
279
+ )
280
+ )
281
+ (intermediate): RobertaIntermediate(
282
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
283
+ )
284
+ (output): RobertaOutput(
285
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
286
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
287
+ (dropout): Dropout(p=0.1, inplace=False)
288
+ )
289
+ )
290
+ )
291
+ )
292
+ (pooler): RobertaPooler(
293
+ (dense): Linear(in_features=768, out_features=768, bias=True)
294
+ (activation): Tanh()
295
+ )
296
+ )
297
+ )
298
+ (word_dropout): WordDropout(p=0.05)
299
+ (locked_dropout): LockedDropout(p=0.5)
300
+ (embedding2nn): Linear(in_features=1536, out_features=1536, bias=True)
301
+ (linear): Linear(in_features=1536, out_features=10, bias=True)
302
+ (beta): 1.0
303
+ (weights): None
304
+ (weight_tensor) None
305
+ )"
306
+ 2021-07-14 12:29:46,928 ----------------------------------------------------------------------------------------------------
307
+ 2021-07-14 12:29:46,928 Corpus: "Corpus: 166 train + 47 dev + 18 test sentences"
308
+ 2021-07-14 12:29:46,928 ----------------------------------------------------------------------------------------------------
309
+ 2021-07-14 12:29:46,929 Parameters:
310
+ 2021-07-14 12:29:46,929 - learning_rate: "5e-05"
311
+ 2021-07-14 12:29:46,929 - mini_batch_size: "64"
312
+ 2021-07-14 12:29:46,930 - patience: "10"
313
+ 2021-07-14 12:29:46,930 - anneal_factor: "0.5"
314
+ 2021-07-14 12:29:46,930 - max_epochs: "20"
315
+ 2021-07-14 12:29:46,930 - shuffle: "True"
316
+ 2021-07-14 12:29:46,931 - train_with_dev: "False"
317
+ 2021-07-14 12:29:46,932 - batch_growth_annealing: "False"
318
+ 2021-07-14 12:29:46,932 ----------------------------------------------------------------------------------------------------
319
+ 2021-07-14 12:29:46,932 Model training base path: "training/flair_ner/14072021_122911"
320
+ 2021-07-14 12:29:46,933 ----------------------------------------------------------------------------------------------------
321
+ 2021-07-14 12:29:46,933 Device: cuda
322
+ 2021-07-14 12:29:46,933 ----------------------------------------------------------------------------------------------------
323
+ 2021-07-14 12:29:46,934 Embeddings storage mode: cpu
324
+ 2021-07-14 12:29:46,935 ----------------------------------------------------------------------------------------------------
325
+ 2021-07-14 12:29:48,214 epoch 1 - iter 1/3 - loss 2.35227370 - samples/sec: 50.10 - lr: 0.000050
326
+ 2021-07-14 12:29:49,437 epoch 1 - iter 2/3 - loss 2.28022432 - samples/sec: 52.38 - lr: 0.000050
327
+ 2021-07-14 12:29:50,199 epoch 1 - iter 3/3 - loss 2.20977402 - samples/sec: 84.16 - lr: 0.000050
328
+ 2021-07-14 12:29:50,201 ----------------------------------------------------------------------------------------------------
329
+ 2021-07-14 12:29:50,202 EPOCH 1 done: loss 2.2098 - lr 0.0000500
330
+ 2021-07-14 12:29:50,546 DEV : loss 1.9138526916503906 - score 0.0
331
+ 2021-07-14 12:29:50,548 BAD EPOCHS (no improvement): 0
332
+ 2021-07-14 12:29:50,973 ----------------------------------------------------------------------------------------------------
333
+ 2021-07-14 12:29:52,207 epoch 2 - iter 1/3 - loss 1.96132076 - samples/sec: 51.98 - lr: 0.000050
334
+ 2021-07-14 12:29:53,488 epoch 2 - iter 2/3 - loss 1.90193379 - samples/sec: 50.02 - lr: 0.000050
335
+ 2021-07-14 12:29:54,256 epoch 2 - iter 3/3 - loss 1.84439631 - samples/sec: 83.49 - lr: 0.000050
336
+ 2021-07-14 12:29:54,258 ----------------------------------------------------------------------------------------------------
337
+ 2021-07-14 12:29:54,259 EPOCH 2 done: loss 1.8444 - lr 0.0000500
338
+ 2021-07-14 12:29:54,601 DEV : loss 1.5503730773925781 - score 0.0
339
+ 2021-07-14 12:29:54,603 BAD EPOCHS (no improvement): 0
340
+ 2021-07-14 12:29:55,347 ----------------------------------------------------------------------------------------------------
341
+ 2021-07-14 12:29:56,677 epoch 3 - iter 1/3 - loss 1.63147676 - samples/sec: 48.19 - lr: 0.000050
342
+ 2021-07-14 12:29:57,914 epoch 3 - iter 2/3 - loss 1.57686120 - samples/sec: 51.79 - lr: 0.000050
343
+ 2021-07-14 12:29:58,748 epoch 3 - iter 3/3 - loss 1.53229376 - samples/sec: 77.01 - lr: 0.000050
344
+ 2021-07-14 12:29:58,749 ----------------------------------------------------------------------------------------------------
345
+ 2021-07-14 12:29:58,750 EPOCH 3 done: loss 1.5323 - lr 0.0000500
346
+ 2021-07-14 12:29:59,154 DEV : loss 1.2592977285385132 - score 0.0
347
+ 2021-07-14 12:29:59,156 BAD EPOCHS (no improvement): 0
348
+ 2021-07-14 12:29:59,889 ----------------------------------------------------------------------------------------------------
349
+ 2021-07-14 12:30:01,249 epoch 4 - iter 1/3 - loss 1.34883869 - samples/sec: 47.11 - lr: 0.000050
350
+ 2021-07-14 12:30:02,708 epoch 4 - iter 2/3 - loss 1.31912410 - samples/sec: 43.91 - lr: 0.000050
351
+ 2021-07-14 12:30:03,591 epoch 4 - iter 3/3 - loss 1.27026923 - samples/sec: 72.69 - lr: 0.000050
352
+ 2021-07-14 12:30:03,593 ----------------------------------------------------------------------------------------------------
353
+ 2021-07-14 12:30:03,594 EPOCH 4 done: loss 1.2703 - lr 0.0000500
354
+ 2021-07-14 12:30:03,987 DEV : loss 1.016648769378662 - score 0.0
355
+ 2021-07-14 12:30:03,989 BAD EPOCHS (no improvement): 0
356
+ 2021-07-14 12:30:04,563 ----------------------------------------------------------------------------------------------------
357
+ 2021-07-14 12:30:05,888 epoch 5 - iter 1/3 - loss 1.12140608 - samples/sec: 48.37 - lr: 0.000050
358
+ 2021-07-14 12:30:07,151 epoch 5 - iter 2/3 - loss 1.08246434 - samples/sec: 50.75 - lr: 0.000050
359
+ 2021-07-14 12:30:07,962 epoch 5 - iter 3/3 - loss 1.04586204 - samples/sec: 79.16 - lr: 0.000050
360
+ 2021-07-14 12:30:07,963 ----------------------------------------------------------------------------------------------------
361
+ 2021-07-14 12:30:07,964 EPOCH 5 done: loss 1.0459 - lr 0.0000500
362
+ 2021-07-14 12:30:08,304 DEV : loss 0.8294103741645813 - score 0.5212
363
+ 2021-07-14 12:30:08,306 BAD EPOCHS (no improvement): 0
364
+ 2021-07-14 12:30:08,788 ----------------------------------------------------------------------------------------------------
365
+ 2021-07-14 12:30:10,005 epoch 6 - iter 1/3 - loss 0.91810364 - samples/sec: 52.62 - lr: 0.000050
366
+ 2021-07-14 12:30:11,278 epoch 6 - iter 2/3 - loss 0.91811162 - samples/sec: 50.35 - lr: 0.000050
367
+ 2021-07-14 12:30:12,059 epoch 6 - iter 3/3 - loss 0.90433153 - samples/sec: 82.14 - lr: 0.000050
368
+ 2021-07-14 12:30:12,061 ----------------------------------------------------------------------------------------------------
369
+ 2021-07-14 12:30:12,062 EPOCH 6 done: loss 0.9043 - lr 0.0000500
370
+ 2021-07-14 12:30:12,432 DEV : loss 0.695007860660553 - score 0.5575
371
+ 2021-07-14 12:30:12,434 BAD EPOCHS (no improvement): 0
372
+ 2021-07-14 12:30:13,158 ----------------------------------------------------------------------------------------------------
373
+ 2021-07-14 12:30:14,391 epoch 7 - iter 1/3 - loss 0.81439382 - samples/sec: 51.99 - lr: 0.000050
374
+ 2021-07-14 12:30:15,642 epoch 7 - iter 2/3 - loss 0.79940459 - samples/sec: 51.23 - lr: 0.000050
375
+ 2021-07-14 12:30:16,406 epoch 7 - iter 3/3 - loss 0.77592629 - samples/sec: 84.00 - lr: 0.000050
376
+ 2021-07-14 12:30:16,408 ----------------------------------------------------------------------------------------------------
377
+ 2021-07-14 12:30:16,409 EPOCH 7 done: loss 0.7759 - lr 0.0000500
378
+ 2021-07-14 12:30:16,760 DEV : loss 0.5981403589248657 - score 0.5526
379
+ 2021-07-14 12:30:16,762 BAD EPOCHS (no improvement): 1
380
+ 2021-07-14 12:30:16,762 ----------------------------------------------------------------------------------------------------
381
+ 2021-07-14 12:30:17,976 epoch 8 - iter 1/3 - loss 0.71924663 - samples/sec: 52.81 - lr: 0.000050
382
+ 2021-07-14 12:30:19,220 epoch 8 - iter 2/3 - loss 0.71743566 - samples/sec: 51.48 - lr: 0.000050
383
+ 2021-07-14 12:30:19,981 epoch 8 - iter 3/3 - loss 0.69340299 - samples/sec: 84.27 - lr: 0.000050
384
+ 2021-07-14 12:30:19,983 ----------------------------------------------------------------------------------------------------
385
+ 2021-07-14 12:30:19,984 EPOCH 8 done: loss 0.6934 - lr 0.0000500
386
+ 2021-07-14 12:30:20,317 DEV : loss 0.5290853977203369 - score 0.5526
387
+ 2021-07-14 12:30:20,319 BAD EPOCHS (no improvement): 2
388
+ 2021-07-14 12:30:20,320 ----------------------------------------------------------------------------------------------------
389
+ 2021-07-14 12:30:21,525 epoch 9 - iter 1/3 - loss 0.60421532 - samples/sec: 53.20 - lr: 0.000050
390
+ 2021-07-14 12:30:22,751 epoch 9 - iter 2/3 - loss 0.60770443 - samples/sec: 52.28 - lr: 0.000050
391
+ 2021-07-14 12:30:23,563 epoch 9 - iter 3/3 - loss 0.62412866 - samples/sec: 79.04 - lr: 0.000050
392
+ 2021-07-14 12:30:23,565 ----------------------------------------------------------------------------------------------------
393
+ 2021-07-14 12:30:23,566 EPOCH 9 done: loss 0.6241 - lr 0.0000500
394
+ 2021-07-14 12:30:23,893 DEV : loss 0.47675958275794983 - score 0.5526
395
+ 2021-07-14 12:30:23,895 BAD EPOCHS (no improvement): 3
396
+ 2021-07-14 12:30:23,896 ----------------------------------------------------------------------------------------------------
397
+ 2021-07-14 12:30:25,112 epoch 10 - iter 1/3 - loss 0.57891500 - samples/sec: 52.72 - lr: 0.000050
398
+ 2021-07-14 12:30:26,338 epoch 10 - iter 2/3 - loss 0.58104303 - samples/sec: 52.29 - lr: 0.000050
399
+ 2021-07-14 12:30:27,101 epoch 10 - iter 3/3 - loss 0.56010119 - samples/sec: 84.07 - lr: 0.000050
400
+ 2021-07-14 12:30:27,103 ----------------------------------------------------------------------------------------------------
401
+ 2021-07-14 12:30:27,104 EPOCH 10 done: loss 0.5601 - lr 0.0000500
402
+ 2021-07-14 12:30:27,421 DEV : loss 0.43612268567085266 - score 0.5526
403
+ 2021-07-14 12:30:27,422 BAD EPOCHS (no improvement): 4
404
+ 2021-07-14 12:30:27,422 ----------------------------------------------------------------------------------------------------
405
+ 2021-07-14 12:30:28,614 epoch 11 - iter 1/3 - loss 0.54033983 - samples/sec: 53.77 - lr: 0.000050
406
+ 2021-07-14 12:30:29,801 epoch 11 - iter 2/3 - loss 0.51631019 - samples/sec: 53.97 - lr: 0.000050
407
+ 2021-07-14 12:30:30,540 epoch 11 - iter 3/3 - loss 0.52065144 - samples/sec: 86.88 - lr: 0.000050
408
+ 2021-07-14 12:30:30,541 ----------------------------------------------------------------------------------------------------
409
+ 2021-07-14 12:30:30,542 EPOCH 11 done: loss 0.5207 - lr 0.0000500
410
+ 2021-07-14 12:30:30,867 DEV : loss 0.40072038769721985 - score 0.5526
411
+ 2021-07-14 12:30:30,868 BAD EPOCHS (no improvement): 5
412
+ 2021-07-14 12:30:30,869 ----------------------------------------------------------------------------------------------------
413
+ 2021-07-14 12:30:32,067 epoch 12 - iter 1/3 - loss 0.53995150 - samples/sec: 53.48 - lr: 0.000050
414
+ 2021-07-14 12:30:33,258 epoch 12 - iter 2/3 - loss 0.51412092 - samples/sec: 53.80 - lr: 0.000050
415
+ 2021-07-14 12:30:34,010 epoch 12 - iter 3/3 - loss 0.51459383 - samples/sec: 85.42 - lr: 0.000050
416
+ 2021-07-14 12:30:34,012 ----------------------------------------------------------------------------------------------------
417
+ 2021-07-14 12:30:34,012 EPOCH 12 done: loss 0.5146 - lr 0.0000500
418
+ 2021-07-14 12:30:34,379 DEV : loss 0.3706240952014923 - score 0.5526
419
+ 2021-07-14 12:30:34,381 BAD EPOCHS (no improvement): 6
420
+ 2021-07-14 12:30:34,381 ----------------------------------------------------------------------------------------------------
421
+ 2021-07-14 12:30:35,616 epoch 13 - iter 1/3 - loss 0.43212149 - samples/sec: 51.89 - lr: 0.000050
422
+ 2021-07-14 12:30:36,820 epoch 13 - iter 2/3 - loss 0.43543930 - samples/sec: 53.21 - lr: 0.000050
423
+ 2021-07-14 12:30:37,571 epoch 13 - iter 3/3 - loss 0.45276287 - samples/sec: 85.45 - lr: 0.000050
424
+ 2021-07-14 12:30:37,573 ----------------------------------------------------------------------------------------------------
425
+ 2021-07-14 12:30:37,574 EPOCH 13 done: loss 0.4528 - lr 0.0000500
426
+ 2021-07-14 12:30:37,915 DEV : loss 0.3449324667453766 - score 0.6404
427
+ 2021-07-14 12:30:37,916 BAD EPOCHS (no improvement): 0
428
+ 2021-07-14 12:30:38,586 ----------------------------------------------------------------------------------------------------
429
+ 2021-07-14 12:30:39,806 epoch 14 - iter 1/3 - loss 0.44912323 - samples/sec: 52.53 - lr: 0.000050
430
+ 2021-07-14 12:30:41,023 epoch 14 - iter 2/3 - loss 0.44336306 - samples/sec: 52.68 - lr: 0.000050
431
+ 2021-07-14 12:30:41,814 epoch 14 - iter 3/3 - loss 0.41765077 - samples/sec: 81.17 - lr: 0.000050
432
+ 2021-07-14 12:30:41,816 ----------------------------------------------------------------------------------------------------
433
+ 2021-07-14 12:30:41,816 EPOCH 14 done: loss 0.4177 - lr 0.0000500
434
+ 2021-07-14 12:30:42,134 DEV : loss 0.325687438249588 - score 0.6784
435
+ 2021-07-14 12:30:42,135 BAD EPOCHS (no improvement): 0
436
+ 2021-07-14 12:30:42,791 ----------------------------------------------------------------------------------------------------
437
+ 2021-07-14 12:30:43,967 epoch 15 - iter 1/3 - loss 0.45451409 - samples/sec: 54.45 - lr: 0.000050
438
+ 2021-07-14 12:30:45,186 epoch 15 - iter 2/3 - loss 0.44515906 - samples/sec: 52.59 - lr: 0.000050
439
+ 2021-07-14 12:30:45,947 epoch 15 - iter 3/3 - loss 0.40854782 - samples/sec: 84.40 - lr: 0.000050
440
+ 2021-07-14 12:30:45,948 ----------------------------------------------------------------------------------------------------
441
+ 2021-07-14 12:30:45,949 EPOCH 15 done: loss 0.4085 - lr 0.0000500
442
+ 2021-07-14 12:30:46,292 DEV : loss 0.30363929271698 - score 0.7281
443
+ 2021-07-14 12:30:46,294 BAD EPOCHS (no improvement): 0
444
+ 2021-07-14 12:30:46,980 ----------------------------------------------------------------------------------------------------
445
+ 2021-07-14 12:30:48,153 epoch 16 - iter 1/3 - loss 0.40387914 - samples/sec: 54.64 - lr: 0.000050
446
+ 2021-07-14 12:30:49,372 epoch 16 - iter 2/3 - loss 0.38225567 - samples/sec: 52.58 - lr: 0.000050
447
+ 2021-07-14 12:30:50,122 epoch 16 - iter 3/3 - loss 0.37938336 - samples/sec: 85.63 - lr: 0.000050
448
+ 2021-07-14 12:30:50,124 ----------------------------------------------------------------------------------------------------
449
+ 2021-07-14 12:30:50,124 EPOCH 16 done: loss 0.3794 - lr 0.0000500
450
+ 2021-07-14 12:30:50,439 DEV : loss 0.2838006317615509 - score 0.7281
451
+ 2021-07-14 12:30:50,440 BAD EPOCHS (no improvement): 0
452
+ 2021-07-14 12:30:51,094 ----------------------------------------------------------------------------------------------------
453
+ 2021-07-14 12:30:52,287 epoch 17 - iter 1/3 - loss 0.39497861 - samples/sec: 53.72 - lr: 0.000050
454
+ 2021-07-14 12:30:53,490 epoch 17 - iter 2/3 - loss 0.38811269 - samples/sec: 53.27 - lr: 0.000050
455
+ 2021-07-14 12:30:54,277 epoch 17 - iter 3/3 - loss 0.37147811 - samples/sec: 81.57 - lr: 0.000050
456
+ 2021-07-14 12:30:54,279 ----------------------------------------------------------------------------------------------------
457
+ 2021-07-14 12:30:54,279 EPOCH 17 done: loss 0.3715 - lr 0.0000500
458
+ 2021-07-14 12:30:54,639 DEV : loss 0.26397019624710083 - score 0.7982
459
+ 2021-07-14 12:30:54,641 BAD EPOCHS (no improvement): 0
460
+ 2021-07-14 12:30:55,341 ----------------------------------------------------------------------------------------------------
461
+ 2021-07-14 12:30:56,520 epoch 18 - iter 1/3 - loss 0.31903756 - samples/sec: 54.38 - lr: 0.000050
462
+ 2021-07-14 12:30:57,751 epoch 18 - iter 2/3 - loss 0.32964711 - samples/sec: 52.06 - lr: 0.000050
463
+ 2021-07-14 12:30:58,515 epoch 18 - iter 3/3 - loss 0.34293939 - samples/sec: 83.99 - lr: 0.000050
464
+ 2021-07-14 12:30:58,516 ----------------------------------------------------------------------------------------------------
465
+ 2021-07-14 12:30:58,517 EPOCH 18 done: loss 0.3429 - lr 0.0000500
466
+ 2021-07-14 12:30:58,834 DEV : loss 0.24780021607875824 - score 0.837
467
+ 2021-07-14 12:30:58,836 BAD EPOCHS (no improvement): 0
468
+ 2021-07-14 12:30:59,528 ----------------------------------------------------------------------------------------------------
469
+ 2021-07-14 12:31:00,715 epoch 19 - iter 1/3 - loss 0.29141665 - samples/sec: 53.99 - lr: 0.000050
470
+ 2021-07-14 12:31:01,909 epoch 19 - iter 2/3 - loss 0.32132708 - samples/sec: 53.66 - lr: 0.000050
471
+ 2021-07-14 12:31:02,701 epoch 19 - iter 3/3 - loss 0.31613552 - samples/sec: 81.04 - lr: 0.000050
472
+ 2021-07-14 12:31:02,702 ----------------------------------------------------------------------------------------------------
473
+ 2021-07-14 12:31:02,702 EPOCH 19 done: loss 0.3161 - lr 0.0000500
474
+ 2021-07-14 12:31:03,045 DEV : loss 0.23076613247394562 - score 0.8333
475
+ 2021-07-14 12:31:03,046 BAD EPOCHS (no improvement): 1
476
+ 2021-07-14 12:31:03,047 ----------------------------------------------------------------------------------------------------
477
+ 2021-07-14 12:31:04,252 epoch 20 - iter 1/3 - loss 0.30364525 - samples/sec: 53.17 - lr: 0.000050
478
+ 2021-07-14 12:31:05,507 epoch 20 - iter 2/3 - loss 0.28965375 - samples/sec: 51.07 - lr: 0.000050
479
+ 2021-07-14 12:31:06,277 epoch 20 - iter 3/3 - loss 0.32431507 - samples/sec: 83.40 - lr: 0.000050
480
+ 2021-07-14 12:31:06,278 ----------------------------------------------------------------------------------------------------
481
+ 2021-07-14 12:31:06,279 EPOCH 20 done: loss 0.3243 - lr 0.0000500
482
+ 2021-07-14 12:31:06,623 DEV : loss 0.22015438973903656 - score 0.807
483
+ 2021-07-14 12:31:06,625 BAD EPOCHS (no improvement): 2
484
+ 2021-07-14 12:31:07,041 ----------------------------------------------------------------------------------------------------
485
+ 2021-07-14 12:31:07,042 Testing using best model ...
486
+ 2021-07-14 12:31:07,043 loading file training/flair_ner/14072021_122911/best-model.pt
487
+ 2021-07-14 12:31:10,530 0.9048 0.9048 0.9048
488
+ 2021-07-14 12:31:10,530
489
+ Results:
490
+ - F1-score (micro) 0.9048
491
+ - F1-score (macro) 0.7574
492
+
493
+ By class:
494
+ duration_br_hr tp: 2 - fp: 0 - fn: 0 - precision: 1.0000 - recall: 1.0000 - f1-score: 1.0000
495
+ duration_br_min tp: 11 - fp: 0 - fn: 1 - precision: 1.0000 - recall: 0.9167 - f1-score: 0.9565
496
+ duration_br_sd tp: 4 - fp: 1 - fn: 0 - precision: 0.8000 - recall: 1.0000 - f1-score: 0.8889
497
+ duration_wt_min tp: 0 - fp: 0 - fn: 2 - precision: 0.0000 - recall: 0.0000 - f1-score: 0.0000
498
+ duration_wt_sd tp: 4 - fp: 2 - fn: 1 - precision: 0.6667 - recall: 0.8000 - f1-score: 0.7273
499
+ nb_rounds tp: 17 - fp: 1 - fn: 0 - precision: 0.9444 - recall: 1.0000 - f1-score: 0.9714
500
+ 2021-07-14 12:31:10,531 ----------------------------------------------------------------------------------------------------